Titre : Redéfinir l’explicabilité : étude de la conception d’une intelligence artificielle explicable en anatomie et cytologie pathologiques Océane Fiant est post-doctorante à l’UTC et sera à partir d’octobre 2024 maître de conférence à l’Université de Côté d’Azur. Résumé : La réponse de l’ingénieur au problème de l’opacité des modèles d’apprentissage automatique consiste soit à […]

Date : 14-15 octobre 2024 Lieu : Hôtel Belambra “Le Domaine du Normont” 36 bis, avenue d’Orléans 91410 Dourdan Programme  

Bénédicte Mélot : Place de l’intelligence artificielle pour évaluer et améliorer l’usage des antibiotiques en médecine générale Morgan Vaterkowski : Conception d’un cadre de caractérisation de l’accessibilité et de l’utilité des données de santé de vie réelle pour l’inclusion de patients atteints de cancer dans des essais cliniques

Pantelis is head of the eHealth Lab at CERTH (Centre for Research and Technology) in Thessaloniki, and will be presenting the team’s activities in the field of artificial intelligence and eHealth.

Alaedine is a new PhD student at Limics, and will present his research subject, as well as a focus on synthetic health data. This presentation explores the role of synthetic data as a promising solution to overcome regulatory barriers in healthcare machine learning. By detailing its methodology, including regulatory compliance, reduced re-identification risks, and usability […]

Title: How can we use hierarchical classification to improve the representation of white blood cell images by foundation models? Summary: In this presentation I will first make an introduction about what is hierarchical classification and how can it be implemented in Deep Learning. I will also introduce DinoV2 architecture that is current state-of-the-art foundation model […]

Abstract: Structural Causal Models (SCMs) offer a powerful framework for understanding and reasoning about causal relationships, particularly in the context of total effects. In this presentation, we will explore a range of established tools for identifying total effects using fully specified Directed Acyclic Graphs (DAGs) derived from SCMs. These tools will be illustrated through two […]